| | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr| | |
| |---------------------------------------|-------|------|-----:|------|-----:|---|-----:| | |
| |mmlu |N/A |none | 0|acc |0.3847|± |0.0040| | |
| | - humanities |N/A |none | 0|acc |0.3598|± |0.0069| | |
| | - formal_logic | 0|none | 0|acc |0.3333|± |0.0422| | |
| | - high_school_european_history | 0|none | 0|acc |0.4424|± |0.0388| | |
| | - high_school_us_history | 0|none | 0|acc |0.4706|± |0.0350| | |
| | - high_school_world_history | 0|none | 0|acc |0.4684|± |0.0325| | |
| | - international_law | 0|none | 0|acc |0.4793|± |0.0456| | |
| | - jurisprudence | 0|none | 0|acc |0.4815|± |0.0483| | |
| | - logical_fallacies | 0|none | 0|acc |0.3988|± |0.0385| | |
| | - moral_disputes | 0|none | 0|acc |0.4335|± |0.0267| | |
| | - moral_scenarios | 0|none | 0|acc |0.2559|± |0.0146| | |
| | - philosophy | 0|none | 0|acc |0.4727|± |0.0284| | |
| | - prehistory | 0|none | 0|acc |0.4321|± |0.0276| | |
| | - professional_law | 0|none | 0|acc |0.2920|± |0.0116| | |
| | - world_religions | 0|none | 0|acc |0.4795|± |0.0383| | |
| | - other |N/A |none | 0|acc |0.4220|± |0.0087| | |
| | - business_ethics | 0|none | 0|acc |0.4600|± |0.0501| | |
| | - clinical_knowledge | 0|none | 0|acc |0.4038|± |0.0302| | |
| | - college_medicine | 0|none | 0|acc |0.3237|± |0.0357| | |
| | - global_facts | 0|none | 0|acc |0.2500|± |0.0435| | |
| | - human_aging | 0|none | 0|acc |0.4305|± |0.0332| | |
| | - management | 0|none | 0|acc |0.4466|± |0.0492| | |
| | - marketing | 0|none | 0|acc |0.5556|± |0.0326| | |
| | - medical_genetics | 0|none | 0|acc |0.4700|± |0.0502| | |
| | - miscellaneous | 0|none | 0|acc |0.4904|± |0.0179| | |
| | - nutrition | 0|none | 0|acc |0.4902|± |0.0286| | |
| | - professional_accounting | 0|none | 0|acc |0.2730|± |0.0266| | |
| | - professional_medicine | 0|none | 0|acc |0.3015|± |0.0279| | |
| | - virology | 0|none | 0|acc |0.3916|± |0.0380| | |
| | - social_sciences |N/A |none | 0|acc |0.4361|± |0.0088| | |
| | - econometrics | 0|none | 0|acc |0.2368|± |0.0400| | |
| | - high_school_geography | 0|none | 0|acc |0.5101|± |0.0356| | |
| | - high_school_government_and_politics| 0|none | 0|acc |0.5648|± |0.0358| | |
| | - high_school_macroeconomics | 0|none | 0|acc |0.3359|± |0.0239| | |
| | - high_school_microeconomics | 0|none | 0|acc |0.3739|± |0.0314| | |
| | - high_school_psychology | 0|none | 0|acc |0.4991|± |0.0214| | |
| | - human_sexuality | 0|none | 0|acc |0.4275|± |0.0434| | |
| | - professional_psychology | 0|none | 0|acc |0.3922|± |0.0198| | |
| | - public_relations | 0|none | 0|acc |0.4000|± |0.0469| | |
| | - security_studies | 0|none | 0|acc |0.4245|± |0.0316| | |
| | - sociology | 0|none | 0|acc |0.5672|± |0.0350| | |
| | - us_foreign_policy | 0|none | 0|acc |0.5500|± |0.0500| | |
| | - stem |N/A |none | 0|acc |0.3349|± |0.0083| | |
| | - abstract_algebra | 0|none | 0|acc |0.3300|± |0.0473| | |
| | - anatomy | 0|none | 0|acc |0.4667|± |0.0431| | |
| | - astronomy | 0|none | 0|acc |0.3947|± |0.0398| | |
| | - college_biology | 0|none | 0|acc |0.4375|± |0.0415| | |
| | - college_chemistry | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - college_computer_science | 0|none | 0|acc |0.3100|± |0.0465| | |
| | - college_mathematics | 0|none | 0|acc |0.2400|± |0.0429| | |
| | - college_physics | 0|none | 0|acc |0.3725|± |0.0481| | |
| | - computer_security | 0|none | 0|acc |0.5000|± |0.0503| | |
| | - conceptual_physics | 0|none | 0|acc |0.3532|± |0.0312| | |
| | - electrical_engineering | 0|none | 0|acc |0.3655|± |0.0401| | |
| | - elementary_mathematics | 0|none | 0|acc |0.2540|± |0.0224| | |
| | - high_school_biology | 0|none | 0|acc |0.4323|± |0.0282| | |
| | - high_school_chemistry | 0|none | 0|acc |0.3005|± |0.0323| | |
| | - high_school_computer_science | 0|none | 0|acc |0.3200|± |0.0469| | |
| | - high_school_mathematics | 0|none | 0|acc |0.2630|± |0.0268| | |
| | - high_school_physics | 0|none | 0|acc |0.3046|± |0.0376| | |
| | - high_school_statistics | 0|none | 0|acc |0.2546|± |0.0297| | |
| | - machine_learning | 0|none | 0|acc |0.2768|± |0.0425| | |